AI agents call tenth_man_history to retrieve information from Tenth Man without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical audit report data for review purposes. It performs a passive query without side effects, making it a Read category operation. The severity is low because querying audit history poses minimal risk; it does not modify systems, execute code, delete data, or affect financial transactions. The confidence is high because the description clearly indicates a read-only query operation.
From the tool's definition Tool description states 'Query past 10th Man audit reports' and 'Returns recent reviews with verdicts, issues found, and agents used' — this is a data retrieval operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Query past 10th Man audit reports from this repository. Returns recent reviews with verdicts, issues found, and agents used. It is categorised as a Read tool in the Tenth Man MCP Server, which means it retrieves data without modifying state.
Register the Tenth Man MCP server in PolicyLayer and add a rule for tenth_man_history: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Tenth Man. Nothing to install.
tenth_man_history is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the tenth_man_history rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for tenth_man_history. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
tenth_man_history is provided by the Tenth Man MCP server (keeganthewhi/tenth-man-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →